Design and testing of a fuzzy logic/neural network hybrid controller for three-pump liquid level/temperature control

The authors describe multivariable, adaptive controllers that incorporate both fuzzy logic rules and neural networks. The controllers were implemented in laboratory trials and were robust, producing smooth temperature and water level response curves with short time constants. The projected role of these intelligent controllers in high-level control applications is discussed. The reasons why intelligent controllers can advantageously replace classical controllers in many situations are outlined.<>